Notebook for Social audit

This is a notebook processing the questionnaire responses for social audit work done with the residents of Sri Tanjung Apartment in USJ 16.

Text in quoted blocks like this as well as data presented in tabular form and graphs can be copied and used in final report

Setup

Quick setup to load the data

%matplotlib inline

import csv
from functools import reduce

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

from sinar_social_audit_2020 import preprocessor, fields, distribution, relation

plt.rcParams['figure.figsize'] = [10, 8]

with open("./responses.csv", "r") as file_responses:
    reader_responses = csv.reader(file_responses)

    headers = tuple(preprocessor.field_name(field) for field in next(reader_responses))

    df = pd.DataFrame(data=reader_responses, columns=headers, dtype=str)

Distribution of responses for each question

These are the distribution of responses for each questions (some further broken down as needed).

Demographic study

Gender

The following cell shows the distribution of gender, unfortunately, as the field was only added after some time the questionnaire went online so. In total there were 28 entries where gender isn't captured.

print(
    "{} entries with no gender information.".format(
        df[df[fields.FIELD_GENDER] == ""][fields.FIELD_GENDER].count()
    )
)

normalized_gender, summary_gender = distribution.distinct(
    df, fields.FIELD_GENDER, "Gender"
)

28 entries with no gender information.

	Frequency
Gender
Lelaki	29
Memilih tidak menjawab	1
Perempuan	52
not captured	28

Age

The following cell shows the age distribution of the respondent.

normalized_age, summary_age = distribution.number(
    df, fields.FIELD_AGE, "Age", (0, 10, 20, 30, 40, 50, 60)
)

	Frequency
Age
(-0.001, 10.0]	1
(10.0, 20.0]	5
(20.0, 30.0]	24
(30.0, 40.0]	53
(40.0, 50.0]	23
(50.0, 60.0]	4

Education level

The following shows the distribution of education level

normalized_edulevel, summary_edulevel = distribution.distinct(
    df, fields.FIELD_EDUCATION_LEVEL, "Education level"
)

	Frequency
Education level
Institusi pengajian tinggi	61
Memilih untuk tidak menjawab	2
Sekolah menengah	47

Employment status

The following shows the distribution of employment

normalized_employment, summary_employment = distribution.distinct(
    df,
    fields.FIELD_EMPLOYMENT_STATUS,
    "Employment status",
    preprocessor.employment_status,
)

	Frequency
Employment status
Bekerja dengan bergaji (sepenuh masa/ separuh masa)	66
Bekerja sendiri/ pemilik perniagaan	16
Memilih tidak menjawab	3
Menganggur / tidak bekerja ( tiada kerja / sedang mencari kerja)	11
Pelajar (sepenuh masa /separuh masa)	6
Tentera / Polis / Badan Beruniform	1
surirumah	7

Household income

The following cell shows the distribution of household income and the respective histogram.

normalized_income, summary_income = distribution.number(
    df, fields.FIELD_HOUSEHOLD_INCOME, "Household income", 8, preprocessor.income
)

	Frequency
Household income
(-8.001, 1000.0]	8
(1000.0, 2000.0]	27
(2000.0, 3000.0]	33
(3000.0, 4000.0]	25
(4000.0, 5000.0]	8
(5000.0, 6000.0]	4
(6000.0, 7000.0]	3
(7000.0, 8000.0]	2

Family size

The following shows the distribution of family size

normalized_family_size, summary_family_size = distribution.distinct(
    df,
    fields.FIELD_FAMILY_SIZE,
    "Family size",
    lambda x: preprocessor.value_integer(x)
    if preprocessor.value_integer(x) <= 10
    else np.nan,
)

	Frequency
Family size
1.0	3
2.0	18
3.0	23
4.0	19
5.0	21
6.0	10
7.0	10
8.0	4
10.0	1

Accessing the Internet and Challenges

How do you access government services

The following shows how respondents access government services, please note that the options are not mutually exclusive

normalized_public_access_method, summary_public_access_method = distribution.mcq(
    df,
    fields.FIELD_PUBLIC_ACCESS_METHOD,
    "Access method",
    (
        "Pejabat jabatan kerajaan",
        "Pusat tumpuan perkhidmatan kerajaan (spt UTC dan RTC)",
        "Kaunter/Pejabat bergerak perkhidmatan kerajaan",
        "Dalam talian",
    ),
)

	Frequency
Access method
Pejabat jabatan kerajaan	32
Pusat tumpuan perkhidmatan kerajaan (spt UTC dan RTC)	24
Kaunter/Pejabat bergerak perkhidmatan kerajaan	11
Dalam talian	80

Do you own and often use these equipments

normalized_owned_devices, summary_owned_devices = distribution.mcq(
    df,
    fields.FIELD_OWNED_DEVICES,
    "Owned devices",
    (
        "Komputer desktop",
        "Laptop(termasuk kompter riba dan netbook)",
        "Tablet (iPad, galaxy tab, dll)",
        "Konsol permainan (Playstation, Nintendo Switch, Xbox)",
        "Telefon pintar",
        "smart tv",
        "Android box",
    ),
)

	Frequency
Owned devices
Komputer desktop	19
Laptop(termasuk kompter riba dan netbook)	48
Tablet (iPad, galaxy tab, dll)	23
Konsol permainan (Playstation, Nintendo Switch, Xbox)	8
Telefon pintar	108
smart tv	1
Android box	1

Do you use internet for as long as you wanted

normalized_sufficient_usage, summary_sufficient_usage = distribution.distinct(
    df, fields.FIELD_SUFFICIENT_USAGE, "Sufficient usage"
)

	Frequency
Sufficient usage
Tidak	33
Tidak pasti/ tidak tahu	9
Ya	68

Have you used free WiFi services in public areas in the past

normalized_used_public_wifi, summary_used_public_wifi = distribution.distinct(
    df, fields.FIELD_USED_PUBLIC_WIFI, "Used public wifi"
)

	Frequency
Used public wifi
Tidak	54
Tidak pasti/ tidak tahu	4
Ya	52

Have you used free WiFi services provided by the government

normalized_used_selangor_wifi, summary_used_selangor_wifi = distribution.distinct(
    df, fields.FIELD_USED_SELANGOR_WIFI, "Used government WiFi"
)

	Frequency
Used government WiFi
Tidak	70
Tidak pasti/ tidak tahu	6
Ya	34

Are you able to work from home

normalized_wfh, summary_wfh = distribution.distinct(
    df, fields.FIELD_CAN_WORK_FROM_HOME, "Able to WFH"
)

	Frequency
Able to WFH
Tidak	18
Tidak pasti/ tidak tahu	19
Ya	73

Are you being comfortable with working from home

normalized_comfortable_wfh, summary_comfortable_wfh = distribution.distinct(
    df, fields.FIELD_COMFY_WORK_FROM_HOME, "Comfortable WFH"
)

	Frequency
Comfortable WFH
Tidak	31
Tidak pasti/ tidak tahu	18
Ya	61

Are your family members (if applicable) able to learn online?

normalized_can_elearn, summary_can_elearn = distribution.distinct(
    df, fields.FIELD_FAMILY_CAN_ELEARN, "Can elearn"
)

	Frequency
Can elearn
Tidak	25
Tidak pasti/ tidak tahu	13
Ya	72

Are they comfortable with learning online?

normalized_comfortable_elearn, summary_comfortable_elearn = distribution.distinct(
    df, fields.FIELD_COMFY_ELEARN, "Comfortable elearn"
)

	Frequency
Comfortable elearn
Tidak	37
Tidak pasti/ tidak tahu	23
Ya	50

How much are you willing to pay monthly for internet access service?

normalized_budget_internet, summary_budget_internet = distribution.number(
    df, fields.FIELD_BUDGET_INTERNET, "budget internet", range(0, 501, 50)
)

	Frequency
budget internet
(-0.001, 50.0]	64
(50.0, 100.0]	34
(100.0, 150.0]	3
(150.0, 200.0]	5
(200.0, 250.0]	0
(250.0, 300.0]	0
(300.0, 350.0]	0
(350.0, 400.0]	0
(400.0, 450.0]	0
(450.0, 500.0]	1

How much are you willing to pay for a new computer or laptop

normalized_budget_computer, summary_budget_computer = distribution.number(
    df, fields.FIELD_BUDGET_COMPUTER, "budget computer", range(0, 801, 100)
)

	Frequency
budget computer
(-0.001, 100.0]	14
(100.0, 200.0]	7
(200.0, 300.0]	7
(300.0, 400.0]	0
(400.0, 500.0]	11
(500.0, 600.0]	0
(600.0, 700.0]	6
(700.0, 800.0]	3

How much are you willing to pay for a new smartphone or tablet?

normalized_budget_mobile, summary_budget_mobile = distribution.number(
    df, fields.FIELD_BUDGET_MOBILE, "budget mobile", range(0, 801, 100)
)

	Frequency
budget mobile
(-0.001, 100.0]	18
(100.0, 200.0]	7
(200.0, 300.0]	9
(300.0, 400.0]	2
(400.0, 500.0]	23
(500.0, 600.0]	5
(600.0, 700.0]	5
(700.0, 800.0]	7

Which of the following devices/services do you think are essential for the time being?

normalized_device_wish, summary_device_wish = distribution.mcq(
    df,
    fields.FIELD_DEVICE_WISH,
    "essential device",
    ("Kemudahan Internet", "Komputer/ laptop", "Kemudahan cetak / printer"),
    lambda x: 'Kemudahan Internet, Komputer/ laptop, Kemudahan cetak / printer' if x == 'semua di atas' else x
)

	Frequency
essential device
Kemudahan Internet	86
Komputer/ laptop	53
Kemudahan cetak / printer	45

other essential devices/services

normalized_device_wish_more, summary_device_wish_more = distribution.mcq(
    df,
    fields.FIELD_DEVICE_WISH_MORE,
    "essential",
    (
        "cellphone",
        "computer",
        "printer",
        "wifi",
        "internet (free) service",
        "internet service",
        "laptop",
        "monetary assistance",
        "smart tv",
        "smartphone",
        "speaker",
        "telephony service",
        "television",
        "internet (unlimited) service",
    ),
    preprocessor.essential_wishlist,
)

	Frequency
essential
cellphone	1
computer	7
printer	9
wifi	3
internet (free) service	2
internet service	7
laptop	10
monetary assistance	2
smart tv	1
smartphone	1
speaker	1
telephony service	1
television	1
internet (unlimited) service	1

Challenges encountered in getting internet access

Problem accessing the internet due to device related challenges

normalized_challenge_device, summary_challenge_device = distribution.ranking(
    df,
    [
        fields.FIELD_INTERNET_PROBLEM_DEVICE_EXPENSIVE,
        fields.FIELD_INTERNET_PROBLEM_NO_DEVICE,
        fields.FIELD_INTERNET_PROBLEM_MANY_BATTERIES,
        fields.FIELD_INTERNET_PROBLEM_ACCESS_PROBLEM,
    ],
    ("A", "B", "C", "D"),
)

	internet_problem_device_expensive	internet_problem_no_device	internet_problem_many_batteries	internet_problem_access_problem
A	67	31	34	55
B	26	38	41	31
C	12	36	27	18
D	5	5	8	6

Problem accessing the internet due to service related challenges

normalized_challenge_service, summary_challenge_service = distribution.ranking(
    df,
    [
        fields.FIELD_INTERNET_PROBLEM_SERVICE_EXPENSIVE,
        fields.FIELD_INTERNET_PROBLEM_NO_COVERAGE,
    ],
    ("A", "B", "C", "D"),
)

	internet_problem_service_expensive	internet_problem_no_coverage
A	58	55
B	34	32
C	15	14
D	3	9

Problem accessing the internet due to technical ability related challenges

normalized_challenge_tech, summary_challenge_tech = distribution.ranking(
    df,
    [
        fields.FIELD_INTERNET_PROBLEM_NO_TIME_LEARN,
        fields.FIELD_INTERNET_PROBLEM_TECHNOLOGY_BARRIER,
        fields.FIELD_INTERNET_PROBLEM_NO_CONFIDENCE_INTERNET,
        fields.FIELD_INTERNET_PROBLEM_NO_INTERNET_SKILL,
        fields.FIELD_INTERNET_PROBLEM_NO_TEACHING,
    ],
    ["A", "B", "C", "D"],
)

	internet_problem_no_time_learn	internet_problem_technology_barrier	internet_problem_no_confidence_internet	internet_problem_no_internet_skill	internet_problem_no_teaching
A	14	16	10	13	14
B	37	35	33	36	34
C	48	47	54	49	51
D	11	12	13	12	11

Problem accessing the internet due to literacy related challenges

normalized_challenge_literacy, summary_challenge_literacy = distribution.ranking(
    df,
    [
        fields.FIELD_INTERNET_PROBLEM_LANGUAGE_BARRIER,
        fields.FIELD_INTERNET_PROBLEM_READ_WRITE_PROBLEM,
    ],
    ["A", "B", "C", "D"],
)

	internet_problem_language_barrier	internet_problem_read_write_problem
A	16	11
B	33	32
C	38	55
D	23	12

Problem accessing the internet due to data privacy concern

normalized_challenge_privacy, summary_challenge_privacy = distribution.ranking(
    df,
    [
        fields.FIELD_INTERNET_PROBLEM_STRANGER_FEAR,
        fields.FIELD_INTERNET_PROBLEM_CONTENT_FEAR,
        fields.FIELD_INTERNET_PROBLEM_IDENTITY_THEFT,
    ],
    ["A", "B", "C", "D"],
)

	internet_problem_stranger_fear	internet_problem_content_fear	internet_problem_identity_theft
A	17	26	30
B	37	33	40
C	42	40	29
D	14	11	11

Problem accessing the internet due to other challenges

normalized_challenge_other, summary_challenge_other = distribution.ranking(
    df,
    [
        fields.FIELD_INTERNET_PROBLEM_NO_TIME_ACCESS,
        fields.FIELD_INTERNET_PROBLEM_DISINTERESTED,
        fields.FIELD_INTERNET_PROBLEM_NO_PERMISSION,
    ],
    ["A", "B", "C", "D"],
)

	internet_problem_no_time_access	internet_problem_disinterested	internet_problem_no_permission
A	12	18	8
B	37	30	33
C	49	49	55
D	12	13	14

What is your goal when accessing the internet

options = (
    (
        "Komunikasi berdasarkan “satu ke satu” (menggunakan mesej segera, chat,  hantar/terima e-mel, panggilan video, panggilan suara)",
        "p2p communication",
    ),
    (
        "Tujuan sosial/ komunikasi ke ramai orang serentak (menhantar mesej ke kumpulan  Whatsapp / Telegram, berkongsi gambar / video / muzik di internet, mengakses media sosial seperti Facebook)",
        "social networking",
    ),
    (
        "Hiburan (spt. bermain online game, mendengar radio atau menonton video / TV / filem /muzik, atau membaca berita hiburan dan gosip)",
        "entertainment",
    ),
    ("Untuk nasihat dan maklumat perubatan / kesihatan", "health"),
    (
        "Mencari maklumat (spt melayari internet, membaca berita atau memeriksa cuaca, membaca maklumat dan artikel sukan terkini, kajian, dan mencari maklumat untuk tujuan peribadi)",
        "research",
    ),
    ("Pendidikan (kursus latihan online, sokongan untuk kerja sekolah)", "education"),
    (
        "Membeli barang (mengkaji barangan atau memesan dan membeli barangan dalam talian)",
        "shopping",
    ),
    ("Perbankan dan perkhidmatan kewangan (menghantar dan menerima wang)", "banking"),
    ("Menyuarakan pendapat terhadap isu yang diambil berat", "activism"),
    (
        "Membuat dan berkongsi / menerbitkan kontent yang boleh dihasilkan sendiri (gambar, blog, video, game, applikasi, kontent social media, article online dan berita)",
        "content creating",
    ),
    ("Mencari kerja / nasihat kerjaya", "career"),
    (
        "Menyokong perusahaan sendiri (pengliklanan, menghubungi pelanggan, membeli barang dan servis online, mengkaji harga barangan)",
        "ecommerce",
    ),
    ("Tidak pasti / tidak tahu", "unsure"),
    ("pendidikan anak home learns", "education"),
)


def goal_preprocess(item):
    return reduce(
        lambda current, incoming: current.replace(incoming[0], incoming[-1]),
        options,
        item,
    )


normalized_goals, summary_goals = distribution.mcq(
    df,
    fields.FIELD_INTERNET_GOAL,
    "goals",
    set(option[-1] for option in options),
    goal_preprocess,
)

	Frequency
goals
banking	93
career	62
activism	51
unsure	1
research	98
ecommerce	66
p2p communication	98
shopping	79
entertainment	70
health	78
social networking	94
content creating	47
education	88

Frequently accessed web services

normalized_frequent_web, summary_frequent_web = distribution.mcq(
    df,
    fields.FIELD_MONTHLY_SOCIAL_MEDIA,
    "frequently accessed",
    (
        "Facebook",
        "Whatsapp",
        "Telegram",
        "Instagram",
        "Shopee",
        "Wechat",
        "Tiktok",
        "Twitter",
        "LinkedIn",
        "Lazada",
        "Google Meet",
        "Jobstreet",
    ),
)

	Frequency
frequently accessed
Facebook	86
Whatsapp	88
Telegram	71
Instagram	79
Shopee	0
Wechat	10
Tiktok	25
Twitter	32
LinkedIn	12
Lazada	46
Google Meet	1
Jobstreet	1

Type of internet service used

normalized_isp, summary_isp = distribution.mcq(
    df,
    fields.FIELD_ISP_TYPE,
    "isp",
    (
        "Rangkaian mudah alih / SIM card",
        "Talian internet tetap /optik fibre",
        "Wifi percuma",
        "Wifi di tempat kerja / institusi pendidikan",
    ),
)

	Frequency
isp
Rangkaian mudah alih / SIM card	98
Talian internet tetap /optik fibre	30
Wifi percuma	14
Wifi di tempat kerja / institusi pendidikan	25

How does the Internet change your life?

Change in social life

normalized_change_social, summary_change_social = distribution.ranking(
    df,
    [
        fields.FIELD_SOCIAL_BETTER_COMMUNICATION,
        fields.FIELD_SOCIAL_BETTER_ENTERTAINMENT,
        fields.FIELD_SOCIAL_NEGLECT_FAMILY_FRIENDS,
    ],
    ("Sangat Setuju", "Setuju", "Neutral", "Tidak Setuju", "Sangat tidak setuju"),
)

	social_better_communication	social_better_entertainment	social_neglect_family_friends
Sangat Setuju	75	54	18
Setuju	30	41	37
Neutral	4	13	26
Tidak Setuju	1	2	22
Sangat tidak setuju	0	0	7

Change in personal finances

normalized_change_financial, summary_change_financial = distribution.ranking(
    df,
    [
        fields.FIELD_BUDGETING_MORE_OPPORTUNITIES,
        fields.FIELD_BUDGETING_BETTER_PLAN,
        fields.FIELD_BUDGETING_MORE_INCOME,
        fields.FIELD_BUDGETING_MORE_SPENDING,
    ],
    ("Sangat Setuju", "Setuju", "Neutral", "Tidak Setuju", "Sangat tidak setuju"),
)

	budgeting_more_opportunities	budgeting_better_plan	budgeting_more_income	budgeting_more_spending
Sangat Setuju	53	46	36	20
Setuju	41	44	43	35
Neutral	15	16	27	30
Tidak Setuju	1	3	3	18
Sangat tidak setuju	0	1	1	7

Change in service access

normalized_change_access, summary_change_access = distribution.ranking(
    df,
    [
        fields.FIELD_ACCESS_FOLLOW_NEWS,
        fields.FIELD_ACCESS_BETTER_HEALTH_SERVICE,
        fields.FIELD_ACCESS_BETTER_OPPORTUNITY,
        fields.FIELD_ACCESS_BETTER_PUBLIC_SERVICE,
    ],
    ("Sangat Setuju", "Setuju", "Neutral", "Tidak Setuju", "Sangat tidak setuju"),
)

	access_follow_news	access_better_health_service	access_better_opportunity	access_better_public_service
Sangat Setuju	69	66	67	68
Setuju	36	42	37	33
Neutral	4	1	4	7
Tidak Setuju	1	1	2	2
Sangat tidak setuju	0	0	0	0

Change in Social / Self-awareness

normalized_change_awareness, summary_change_awareness = distribution.ranking(
    df,
    [
        fields.FIELD_AWARENESS_MORE_RESPECTED,
        fields.FIELD_AWARENESS_MORE_CONFIDENCE,
        fields.FIELD_AWARENESS_MORE_PROUD,
        fields.FIELD_AWARENESS_MORE_VOICE,
        fields.FIELD_AWARENESS_MORE_CONTROLLED,
        fields.FIELD_AWARENESS_MORE_CONSTRAINED,
    ],
    ("Sangat Setuju", "Setuju", "Neutral", "Tidak Setuju", "Sangat tidak setuju"),
)

	awareness_more_respected	awareness_more_confidence	awareness_more_proud	awareness_more_voice	awareness_more_controlled	awareness_more_constrained
Sangat Setuju	18	27	24	28	16	11
Setuju	48	54	58	57	28	26
Neutral	38	26	25	22	30	27
Tidak Setuju	6	3	3	3	25	29
Sangat tidak setuju	0	0	0	0	11	17

Your opinion on the use of the internet in a family

normalized_opinion_family, summary_opinion_family = distribution.ranking(
    df,
    [
        fields.FIELD_INTERNET_OPINION_WIFE_CHECK_HUSBAND,
        fields.FIELD_INTERNET_OPINION_HUSBAND_CHECK_WIFE,
        fields.FIELD_INTERNET_OPINION_FEMALE_SAFETY,
    ],
    ("Sangat Setuju", "Setuju", "Neutral", "Tidak Setuju", "Sangat tidak setuju"),
)

	internet_opinion_wife_check_husband	internet_opinion_husband_check_wife	internet_opinion_female_safety
Sangat Setuju	28	29	12
Setuju	43	40	35
Neutral	28	29	34
Tidak Setuju	10	10	20
Sangat tidak setuju	1	2	9

Your opinion on the use of the internet based on personal experience

normalized_opinion_personal, summary_opinion_personal = distribution.ranking(
    df,
    [
        fields.FIELD_INTERNET_OPINION_INSECURE_WITHOUT,
        fields.FIELD_INTERNET_OPINION_INTERNET_MORE_CONFUSION,
        fields.FIELD_INTERNET_OPINION_INTERNET_FEEL_SAFE,
        fields.FIELD_INTERNET_OPINION_TRUST_INFO,
        fields.FIELD_INTERNET_OPINION_CHANGE_LIFE,
        fields.FIELD_INTERNET_OPINION_WASTE_TIME,
        fields.FIELD_INTERNET_OPINION_SELECTED_NEED,
    ],
    ("Sangat Setuju", "Setuju", "Neutral", "Tidak Setuju", "Sangat tidak setuju"),
)

	internet_opinion_insecure_without	internet_opinion_internet_more_confusion	internet_opinion_internet_feel_safe	internet_opinion_trust_info	internet_opinion_change_life	internet_opinion_waste_time	internet_opinion_selected_need
Sangat Setuju	29	15	22	18	25	14	12
Setuju	46	32	47	54	52	41	43
Neutral	25	30	36	34	29	31	23
Tidak Setuju	8	28	5	4	4	21	26
Sangat tidak setuju	2	5	0	0	0	3	6

What makes you worried about the internet?

normalized_challenge_tech, summary_challenge_tech = distribution.ranking(
    df,
    [
        fields.FIELD_INTERNET_PROBLEM_STRANGER_FEAR,
        fields.FIELD_INTERNET_PROBLEM_CONTENT_FEAR,
        fields.FIELD_INTERNET_PROBLEM_IDENTITY_THEFT,
    ],
    ['A', 'B', 'C', 'D']
)

	internet_problem_stranger_fear	internet_problem_content_fear	internet_problem_identity_theft
A	17	26	30
B	37	33	40
C	42	40	29
D	14	11	11

Have you experienced the following while using the internet?

normalized_experience_harassment, summary_experience_harassment = distribution.ranking(
    df,
    [
        fields.FIELD_EXPERIENCE_HARASSMENT,
        fields.FIELD_EXPERIENCE_THREAT,
        fields.FIELD_EXPERIENCE_INAPPROPRIATE,
        fields.FIELD_EXPERIENCE_DOXX,
    ],
    (
        "Sentiasa",
        "Sering kali",
        "Kadang kala",
        "Tidak pernah",
        "Tidak pasti/tidak tahu",
    ),
)

	experience_harassment	experience_threat	experience_inappropriate	experience_doxx
Sentiasa	6	7	7	8
Sering kali	34	28	32	29
Kadang kala	26	18	31	19
Tidak pernah	36	52	33	46
Tidak pasti/tidak tahu	8	5	7	8

Do you agree with the following

normalized_opinion_personal, summary_opinion_personal = distribution.ranking(
    df,
    [
        fields.FIELD_AGREE_ON_PRIVACY,
        fields.FIELD_AGREE_ON_INAPPROPRIATE,
        fields.FIELD_AGREE_ON_STRANGER,
    ],
    ("Sangat Setuju", "Setuju", "Neutral", "Tidak Setuju", "Sangat tidak setuju"),
)

	agree_on_privacy	agree_on_inappropriate	agree_on_stranger
Sangat Setuju	35	36	35
Setuju	47	46	48
Neutral	23	19	20
Tidak Setuju	4	7	6
Sangat tidak setuju	1	2	1

Your family does not like you to access the internet

normalized_family_permission, summary_family_permission = distribution.distinct(
    df, fields.FIELD_AGREE_ON_FAMILY_DISPROVAL, "family disproval"
)

	Frequency
family disproval
Neutral	22
Sangat Setuju	7
Sangat tidak setuju	15
Setuju	28
Tidak Setuju	38

Correlation study

This is the part where I start calculating correlation.

vs Household income

Correlation between household income and the methods used to access government service

We fail to reject the hypothesis where there household income is independent from the method used to access the government service at alpha value being set to 0.05 (Which means the same conclusion can be drawn 95% of the time should this study is repeated). Therefore no further study was conducted to test for correlation between the two factors.

income_vs_public_access_method = relation.interval_vs_mcq(
    normalized_income,
    normalized_public_access_method,
    summary_income.index,
)

relation.independence_check(income_vs_public_access_method, 0.05)

	Pejabat jabatan kerajaan	Pusat tumpuan perkhidmatan kerajaan (spt UTC dan RTC)	Kaunter/Pejabat bergerak perkhidmatan kerajaan	Dalam talian
Household income
(-8.001, 1000.0]	3	1	0	4
(1000.0, 2000.0]	7	7	6	18
(2000.0, 3000.0]	8	6	0	25
(3000.0, 4000.0]	6	6	3	19
(4000.0, 5000.0]	5	2	0	5
(5000.0, 6000.0]	2	2	2	4
(6000.0, 7000.0]	0	0	0	3
(7000.0, 8000.0]	1	0	0	2

Failed to reject H_0 at alpha=0.05 since test statistic chi2=19.30038826772428 < 32.670573340917315

True

Correlation between household income vs the ownership of different types of devices

We fail to reject the hypothesis where there household income is independent from the ownership of different types of devices at alpha value being set to 0.05.

income_vs_ownership = relation.interval_vs_mcq(
    normalized_income,
    normalized_owned_devices,
    summary_income.index
)

relation.independence_check(income_vs_ownership, 0.05)

	Komputer desktop	Laptop(termasuk kompter riba dan netbook)	Tablet (iPad, galaxy tab, dll)	Konsol permainan (Playstation, Nintendo Switch, Xbox)	Telefon pintar	smart tv	Android box
Household income
(-8.001, 1000.0]	0	3	0	0	8	0	0
(1000.0, 2000.0]	2	6	3	0	26	0	0
(2000.0, 3000.0]	6	15	8	3	33	1	1
(3000.0, 4000.0]	2	12	4	3	25	0	0
(4000.0, 5000.0]	3	3	4	0	7	0	0
(5000.0, 6000.0]	3	4	1	0	4	0	0
(6000.0, 7000.0]	1	3	2	2	3	0	0
(7000.0, 8000.0]	2	2	1	0	2	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=37.978699912975614 < 58.12403768086803

True

Household income vs whether respondents get to access the internet as much as they desire

We fail to reject the hypothesis where there household income is independent from whether respondents get to access the internet as much as he/she desires at alpha value being set to 0.05.

income_vs_sufficient_usage = relation.interval_vs_distinct(
    normalized_income,
    normalized_sufficient_usage,
    summary_income.index
)

relation.independence_check(income_vs_sufficient_usage, 0.05)

	Tidak	Ya	Tidak pasti/ tidak tahu
Household income
(-8.001, 1000.0]	2	5	1
(1000.0, 2000.0]	5	16	6
(2000.0, 3000.0]	12	21	0
(3000.0, 4000.0]	9	14	2
(4000.0, 5000.0]	2	6	0
(5000.0, 6000.0]	3	1	0
(6000.0, 7000.0]	0	3	0
(7000.0, 8000.0]	0	2	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=19.509733775665147 < 23.684791304840576

True

Household income vs prior experience in usage of public wifi

We fail to reject the hypothesis where there household income is independent from whether respondents used public wifi at alpha value being set to 0.05.

income_vs_used_public_wifi = relation.interval_vs_distinct(
    normalized_income,
    normalized_used_public_wifi,
    summary_income.index
)

relation.independence_check(income_vs_used_public_wifi, 0.05)

	Tidak	Tidak pasti/ tidak tahu	Ya
Household income
(-8.001, 1000.0]	4	1	3
(1000.0, 2000.0]	14	0	13
(2000.0, 3000.0]	12	2	19
(3000.0, 4000.0]	10	0	15
(4000.0, 5000.0]	7	0	1
(5000.0, 6000.0]	2	1	1
(6000.0, 7000.0]	3	0	0
(7000.0, 8000.0]	2	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=22.836703334388524 < 23.684791304840576

True

Household income vs prior experience in usage of public wifi provided by the government

We fail to reject the hypothesis where there household income is independent from whether respondents used public wifi provided by the government at alpha value being set to 0.05.

income_vs_used_selangor_wifi = relation.interval_vs_distinct(
    normalized_income,
    normalized_used_selangor_wifi,
    summary_income.index
)

relation.independence_check(income_vs_used_selangor_wifi, 0.05)

	Tidak	Ya	Tidak pasti/ tidak tahu
Household income
(-8.001, 1000.0]	6	1	1
(1000.0, 2000.0]	15	10	2
(2000.0, 3000.0]	22	10	1
(3000.0, 4000.0]	14	11	0
(4000.0, 5000.0]	5	2	1
(5000.0, 6000.0]	3	0	1
(6000.0, 7000.0]	3	0	0
(7000.0, 8000.0]	2	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=13.74350347546426 < 23.684791304840576

True

Household income vs ability to work from home

We fail to reject the hypothesis where there household income is independent from whether respondents could work from home provided by the government at alpha value being set to 0.05.

income_vs_wfh = relation.interval_vs_distinct(
    normalized_income,
    normalized_wfh,
    summary_income.index
)

relation.independence_check(income_vs_wfh, 0.05)

	Tidak	Ya	Tidak pasti/ tidak tahu
Household income
(-8.001, 1000.0]	2	6	0
(1000.0, 2000.0]	4	16	7
(2000.0, 3000.0]	5	20	8
(3000.0, 4000.0]	6	17	2
(4000.0, 5000.0]	1	6	1
(5000.0, 6000.0]	0	4	0
(6000.0, 7000.0]	0	2	1
(7000.0, 8000.0]	0	2	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=10.768244887120556 < 23.684791304840576

True

Household income vs Comfortable working from home

We fail to reject the hypothesis where there household income is independent from whether respondents could work from home comfortably provided by the government at alpha value being set to 0.05.

income_vs_comfortable_wfh = relation.interval_vs_distinct(
    normalized_income,
    normalized_comfortable_wfh,
    summary_income.index
)

relation.independence_check(income_vs_comfortable_wfh, 0.05)

	Tidak	Ya	Tidak pasti/ tidak tahu
Household income
(-8.001, 1000.0]	3	5	0
(1000.0, 2000.0]	6	17	4
(2000.0, 3000.0]	8	16	9
(3000.0, 4000.0]	6	16	3
(4000.0, 5000.0]	1	5	2
(5000.0, 6000.0]	4	0	0
(6000.0, 7000.0]	2	1	0
(7000.0, 8000.0]	1	1	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=20.263573609451747 < 23.684791304840576

True

Household income vs can e-learn

income_vs_can_elearn = relation.interval_vs_distinct(
    normalized_income,
    normalized_can_elearn,
    summary_income.index
)

relation.independence_check(income_vs_can_elearn, 0.05)

	Ya	Tidak	Tidak pasti/ tidak tahu
Household income
(-8.001, 1000.0]	5	2	1
(1000.0, 2000.0]	17	6	4
(2000.0, 3000.0]	20	9	4
(3000.0, 4000.0]	17	7	1
(4000.0, 5000.0]	6	1	1
(5000.0, 6000.0]	4	0	0
(6000.0, 7000.0]	1	0	2
(7000.0, 8000.0]	2	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=14.751114988920545 < 23.684791304840576

True

Household income vs comfortable e-learn

income_vs_comfortable_elearn = relation.interval_vs_distinct(
    normalized_income,
    normalized_comfortable_elearn,
    summary_income.index
)

relation.independence_check(income_vs_comfortable_elearn, 0.05)

	Tidak	Ya	Tidak pasti/ tidak tahu
Household income
(-8.001, 1000.0]	3	4	1
(1000.0, 2000.0]	9	12	6
(2000.0, 3000.0]	9	15	9
(3000.0, 4000.0]	10	12	3
(4000.0, 5000.0]	1	5	2
(5000.0, 6000.0]	4	0	0
(6000.0, 7000.0]	0	1	2
(7000.0, 8000.0]	1	1	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=16.919992557775167 < 23.684791304840576

True

Household income vs budget for internet access

income_vs_budget_internet = relation.interval_vs_interval(
    normalized_income,
    normalized_budget_internet,
    summary_income.index,
    summary_budget_internet.index,
)

relation.independence_check(income_vs_budget_internet, 0.05)

relation.correlation_check(income_vs_budget_internet, alpha=0.05, method="spearman")

budget internet	(-0.001, 50.0]	(50.0, 100.0]	(100.0, 150.0]	(150.0, 200.0]	(200.0, 250.0]	(250.0, 300.0]	(300.0, 350.0]	(350.0, 400.0]	(400.0, 450.0]	(450.0, 500.0]
Household income
(-8.001, 1000.0]	5	2	0	0	0	0	0	0	0	0
(1000.0, 2000.0]	21	5	0	0	0	0	0	0	0	0
(2000.0, 3000.0]	20	10	2	0	0	0	0	0	0	0
(3000.0, 4000.0]	13	10	0	1	0	0	0	0	0	1
(4000.0, 5000.0]	5	2	0	1	0	0	0	0	0	0
(5000.0, 6000.0]	0	3	0	1	0	0	0	0	0	0
(6000.0, 7000.0]	0	0	1	2	0	0	0	0	0	0
(7000.0, 8000.0]	0	2	0	0	0	0	0	0	0	0

H_0 is rejected at alpha=0.05 since test statistic chi2=64.99069264548768 >= 41.33713815142739
The negative correlation is high at rs=-0.7856457858243782.
Failed to reject H_0 at alpha=0.05 since test statistic T=-2.1994988691951067 and critical region=±3.182446305284263. 
Hence, for budget internet at (-0.001, 50.0], the correlation IS NOT significant.

The negative correlation is some at rs=-0.45420146992971866.
Failed to reject H_0 at alpha=0.05 since test statistic T=-0.8830406415531037 and critical region=±3.182446305284263. 
Hence, for budget internet at (50.0, 100.0], the correlation IS NOT significant.

The correlation is very low at rs=0.06234796863885497.
Failed to reject H_0 at alpha=0.05 since test statistic T=0.10820035616009188 and critical region=±3.182446305284263. 
Hence, for budget internet at (100.0, 150.0], the correlation IS NOT significant.

The correlation is some at rs=0.495558504409436.
Failed to reject H_0 at alpha=0.05 since test statistic T=0.9882082044615871 and critical region=±3.182446305284263. 
Hence, for budget internet at (150.0, 200.0], the correlation IS NOT significant.

The negative correlation is very low at rs=-0.08247860988423225.
Failed to reject H_0 at alpha=0.05 since test statistic T=-0.14334554477024897 and critical region=±3.182446305284263. 
Hence, for budget internet at (450.0, 500.0], the correlation IS NOT significant.

	Correlation
budget internet
(-0.001, 50.0]	-0.785646
(50.0, 100.0]	-0.454201
(100.0, 150.0]	0.062348
(150.0, 200.0]	0.495559
(450.0, 500.0]	-0.082479

Household income vs Budget for computer / laptop

income_vs_budget_computer = relation.interval_vs_interval(
    normalized_income,
    normalized_budget_computer,
    summary_income.index,
    summary_budget_computer.index,
)

relation.independence_check(income_vs_budget_computer, 0.05)

budget computer	(-0.001, 100.0]	(100.0, 200.0]	(200.0, 300.0]	(300.0, 400.0]	(400.0, 500.0]	(500.0, 600.0]	(600.0, 700.0]	(700.0, 800.0]
Household income
(-8.001, 1000.0]	2	0	0	0	0	0	1	0
(1000.0, 2000.0]	5	2	2	0	5	0	0	1
(2000.0, 3000.0]	4	3	2	0	1	0	3	0
(3000.0, 4000.0]	2	1	3	0	4	0	2	0
(4000.0, 5000.0]	1	1	0	0	0	0	0	2
(5000.0, 6000.0]	0	0	0	0	0	0	0	0
(6000.0, 7000.0]	0	0	0	0	0	0	0	0
(7000.0, 8000.0]	0	0	0	0	1	0	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=32.17702297702297 < 37.65248413348277

True

Household income vs budget for mobile devices

income_vs_budget_mobile = relation.interval_vs_interval(
    normalized_income,
    normalized_budget_mobile,
    summary_income.index,
    summary_budget_mobile.index,
)

relation.independence_check(income_vs_budget_mobile, 0.05)

budget mobile	(-0.001, 100.0]	(100.0, 200.0]	(200.0, 300.0]	(300.0, 400.0]	(400.0, 500.0]	(500.0, 600.0]	(600.0, 700.0]	(700.0, 800.0]
Household income
(-8.001, 1000.0]	3	0	0	0	0	1	1	0
(1000.0, 2000.0]	7	3	3	1	3	1	0	3
(2000.0, 3000.0]	5	2	3	1	11	1	2	1
(3000.0, 4000.0]	2	1	3	0	6	2	2	1
(4000.0, 5000.0]	1	1	0	0	2	0	0	0
(5000.0, 6000.0]	0	0	0	0	0	0	0	0
(6000.0, 7000.0]	0	0	0	0	0	0	0	1
(7000.0, 8000.0]	0	0	0	0	1	0	0	1

Failed to reject H_0 at alpha=0.05 since test statistic chi2=39.14368833672451 < 58.12403768086803

True

vs Education level

ranked_edulevel = pd.Series(
    [
        "Sekolah rendah",
        "Sekolah menengah",
        "Institusi pengajian tinggi",
    ],
    name=fields.FIELD_EDUCATION_LEVEL,
)

Correlation between education level and the methods used to access government service

edulevel_vs_public_access_method = relation.distinct_vs_mcq(
    normalized_edulevel,
    normalized_public_access_method,
    ranked_edulevel
)

relation.independence_check(edulevel_vs_public_access_method, 0.05)

	Pejabat jabatan kerajaan	Pusat tumpuan perkhidmatan kerajaan (spt UTC dan RTC)	Kaunter/Pejabat bergerak perkhidmatan kerajaan	Dalam talian
education_level
Sekolah rendah	0	0	0	0
Sekolah menengah	10	11	4	29
Institusi pengajian tinggi	20	13	7	51

Failed to reject H_0 at alpha=0.05 since test statistic chi2=0.9913523976023976 < 7.814727903251179

True

Correlation between education level vs the ownership of different types of devices

edulevel_vs_ownership = relation.distinct_vs_mcq(
    normalized_edulevel, normalized_owned_devices, ranked_edulevel
)

relation.independence_check(edulevel_vs_ownership, 0.05) or relation.correlation_check(
    edulevel_vs_ownership, alpha=0.05, method="spearman"
)

	Komputer desktop	Laptop(termasuk kompter riba dan netbook)	Tablet (iPad, galaxy tab, dll)	Konsol permainan (Playstation, Nintendo Switch, Xbox)	Telefon pintar	smart tv	Android box
education_level
Sekolah rendah	0	0	0	0	0	0	0
Sekolah menengah	4	9	5	4	46	1	1
Institusi pengajian tinggi	15	37	17	4	60	0	0

H_0 is rejected at alpha=0.05 since test statistic chi2=15.773935788362264 >= 12.591587243743977
The negative correlation is very high at rs=-0.9999999999999999.
H_0 is rejected at alpha=0.05 since test statistic T=-134217727.99999999, and critical region=±2.7764451051977987. 
Hence, for None at Komputer desktop, the correlation IS significant.

The negative correlation is very high at rs=-0.9999999999999999.
H_0 is rejected at alpha=0.05 since test statistic T=-134217727.99999999, and critical region=±2.7764451051977987. 
Hence, for None at Laptop(termasuk kompter riba dan netbook), the correlation IS significant.

The negative correlation is very high at rs=-0.9999999999999999.
H_0 is rejected at alpha=0.05 since test statistic T=-134217727.99999999, and critical region=±2.7764451051977987. 
Hence, for None at Tablet (iPad, galaxy tab, dll), the correlation IS significant.

The negative correlation is very high at rs=-0.9999999999999999.
H_0 is rejected at alpha=0.05 since test statistic T=-134217727.99999999, and critical region=±2.7764451051977987. 
Hence, for None at Telefon pintar, the correlation IS significant.

The correlation is very high at rs=0.9999999999999999.
H_0 is rejected at alpha=0.05 since test statistic T=134217727.99999999, and critical region=±2.7764451051977987. 
Hence, for None at smart tv, the correlation IS significant.

The correlation is very high at rs=0.9999999999999999.
H_0 is rejected at alpha=0.05 since test statistic T=134217727.99999999, and critical region=±2.7764451051977987. 
Hence, for None at Android box, the correlation IS significant.

	Correlation
Komputer desktop	-1.0
Laptop(termasuk kompter riba dan netbook)	-1.0
Tablet (iPad, galaxy tab, dll)	-1.0
Telefon pintar	-1.0
smart tv	1.0
Android box	1.0

Education level vs whether respondents get to access the internet as much as they desire

edulevel_vs_sufficient_usage = relation.distinct_vs_distinct(
    normalized_edulevel, normalized_sufficient_usage, ranked_edulevel
)

relation.independence_check(edulevel_vs_sufficient_usage, 0.05) 

sufficient_usage	Tidak	Ya	Tidak pasti/ tidak tahu
education_level
Sekolah rendah	0	0	0
Sekolah menengah	12	30	5
Institusi pengajian tinggi	20	37	4

Failed to reject H_0 at alpha=0.05 since test statistic chi2=1.045203004857124 < 5.991464547107979

True

Education level vs prior experience in usage of public wifi

edulevel_vs_used_public_wifi = relation.distinct_vs_distinct(
    normalized_edulevel, normalized_used_public_wifi, ranked_edulevel
)

relation.independence_check(
    edulevel_vs_used_public_wifi, 0.05
) or relation.correlation_check(
    edulevel_vs_used_public_wifi, alpha=0.05, method="spearman"
)

used_public_wifi	Tidak	Tidak pasti/ tidak tahu	Ya
education_level
Sekolah rendah	0	0	0
Sekolah menengah	27	1	19
Institusi pengajian tinggi	27	2	32

Failed to reject H_0 at alpha=0.05 since test statistic chi2=1.8635589568928366 < 5.991464547107979

True

Education level vs prior experience in usage of public wifi provided by the government

edulevel_vs_used_selangor_wifi = relation.distinct_vs_distinct(
    normalized_edulevel, normalized_used_selangor_wifi, ranked_edulevel
)

relation.independence_check(
    edulevel_vs_used_selangor_wifi, 0.05
) or relation.correlation_check(
    edulevel_vs_used_selangor_wifi, alpha=0.05, method="spearman"
)

used_selangor_wifi	Tidak	Ya	Tidak pasti/ tidak tahu
education_level
Sekolah rendah	0	0	0
Sekolah menengah	36	9	2
Institusi pengajian tinggi	33	25	3

H_0 is rejected at alpha=0.05 since test statistic chi2=6.14834758701406 >= 5.991464547107979
The correlation is very high at rs=0.9999999999999999.
H_0 is rejected at alpha=0.05 since test statistic T=67108863.99999999, and critical region=±12.706204736432095. 
Hence, for used_selangor_wifi at Tidak, the correlation IS significant.

The negative correlation is very high at rs=-0.9999999999999999.
H_0 is rejected at alpha=0.05 since test statistic T=-67108863.99999999, and critical region=±12.706204736432095. 
Hence, for used_selangor_wifi at Ya, the correlation IS significant.

The negative correlation is very high at rs=-0.9999999999999999.
H_0 is rejected at alpha=0.05 since test statistic T=-67108863.99999999, and critical region=±12.706204736432095. 
Hence, for used_selangor_wifi at Tidak pasti/ tidak tahu, the correlation IS significant.

	Correlation
used_selangor_wifi
Tidak	1.0
Ya	-1.0
Tidak pasti/ tidak tahu	-1.0

Education level vs ability to work from home

edulevel_vs_wfh = relation.distinct_vs_distinct(
    normalized_edulevel,
    normalized_wfh,
    ranked_edulevel
)

relation.independence_check(edulevel_vs_wfh, 0.05)

can_work_from_home	Tidak	Ya	Tidak pasti/ tidak tahu
education_level
Sekolah rendah	0	0	0
Sekolah menengah	9	28	10
Institusi pengajian tinggi	8	45	8

Failed to reject H_0 at alpha=0.05 since test statistic chi2=2.466583116611911 < 5.991464547107979

True

Education level vs Comfortable working from home

edulevel_vs_comfortable_wfh = relation.distinct_vs_distinct(
    normalized_edulevel,
    normalized_comfortable_wfh,
    ranked_edulevel
)

relation.independence_check(edulevel_vs_comfortable_wfh, 0.05)

comfy_work_from_home	Tidak	Ya	Tidak pasti/ tidak tahu
education_level
Sekolah rendah	0	0	0
Sekolah menengah	14	25	8
Institusi pengajian tinggi	16	36	9

Failed to reject H_0 at alpha=0.05 since test statistic chi2=0.3671175908880996 < 5.991464547107979

True

Education level vs can e-learn

edulevel_vs_can_elearn = relation.distinct_vs_distinct(
    normalized_edulevel,
    normalized_can_elearn,
    ranked_edulevel
)

relation.independence_check(edulevel_vs_can_elearn, 0.05)

family_can_elearn	Ya	Tidak	Tidak pasti/ tidak tahu
education_level
Sekolah rendah	0	0	0
Sekolah menengah	35	8	4
Institusi pengajian tinggi	37	16	8

Failed to reject H_0 at alpha=0.05 since test statistic chi2=2.279037321241716 < 5.991464547107979

True

Education level vs comfortable e-learn

edulevel_vs_comfortable_elearn = relation.distinct_vs_distinct(
    normalized_edulevel, normalized_comfortable_elearn, ranked_edulevel
)

relation.independence_check(
    edulevel_vs_comfortable_elearn, 0.05
) or relation.correlation_check(
    edulevel_vs_comfortable_elearn, alpha=0.05, method="spearman"
)

comfy_elearn	Tidak	Ya	Tidak pasti/ tidak tahu
education_level
Sekolah rendah	0	0	0
Sekolah menengah	13	25	9
Institusi pengajian tinggi	23	25	13

Failed to reject H_0 at alpha=0.05 since test statistic chi2=1.719123569141009 < 5.991464547107979

True

Education level vs budget for internet access

edulevel_vs_budget_internet = relation.distinct_vs_interval(
    normalized_edulevel,
    normalized_budget_internet,
    ranked_edulevel,
    summary_budget_internet.index,
)

relation.independence_check(
    edulevel_vs_budget_internet, 0.05
) or relation.correlation_check(
    edulevel_vs_budget_internet, alpha=0.05, method="spearman"
)

budget internet	(-0.001, 50.0]	(50.0, 100.0]	(100.0, 150.0]	(150.0, 200.0]	(200.0, 250.0]	(250.0, 300.0]	(300.0, 350.0]	(350.0, 400.0]	(400.0, 450.0]	(450.0, 500.0]
education_level
Sekolah rendah	0	0	0	0	0	0	0	0	0	0
Sekolah menengah	29	13	1	2	0	0	0	0	0	0
Institusi pengajian tinggi	34	21	2	3	0	0	0	0	0	1

Failed to reject H_0 at alpha=0.05 since test statistic chi2=1.4299982822515775 < 9.487729036781154

True

Education level vs Budget for computer / laptop

edulevel_vs_budget_computer = relation.distinct_vs_interval(
    normalized_edulevel,
    normalized_budget_computer,
    ranked_edulevel,
    summary_budget_computer.index,
)

relation.independence_check(
    edulevel_vs_budget_computer, 0.05
) or relation.correlation_check(edulevel_vs_budget_computer, 0.05, method="spearman")

budget computer	(-0.001, 100.0]	(100.0, 200.0]	(200.0, 300.0]	(300.0, 400.0]	(400.0, 500.0]	(500.0, 600.0]	(600.0, 700.0]	(700.0, 800.0]
education_level
Sekolah rendah	0	0	0	0	0	0	0	0
Sekolah menengah	9	5	3	0	2	0	3	1
Institusi pengajian tinggi	5	2	4	0	9	0	3	2

Failed to reject H_0 at alpha=0.05 since test statistic chi2=7.288627893845285 < 11.070497693516351

True

Education level vs budget for mobile devices

edulevel_vs_budget_mobile = relation.distinct_vs_interval(
    normalized_edulevel,
    normalized_budget_mobile,
    ranked_edulevel,
    summary_budget_mobile.index,
)

relation.independence_check(
    edulevel_vs_budget_mobile, 0.05
) or relation.correlation_check(edulevel_vs_budget_mobile, 0.05, method="spearman")

budget mobile	(-0.001, 100.0]	(100.0, 200.0]	(200.0, 300.0]	(300.0, 400.0]	(400.0, 500.0]	(500.0, 600.0]	(600.0, 700.0]	(700.0, 800.0]
education_level
Sekolah rendah	0	0	0	0	0	0	0	0
Sekolah menengah	12	4	3	1	10	1	1	2
Institusi pengajian tinggi	6	3	6	1	13	4	4	5

Failed to reject H_0 at alpha=0.05 since test statistic chi2=7.662675504984604 < 14.067140449340169

True

vs Age

Age vs method used to access government service

age_vs_public_access_method = relation.interval_vs_mcq(
    normalized_age, normalized_public_access_method, summary_age.index
)

relation.independence_check(
    age_vs_public_access_method, 0.05
) or relation.correlation_check(age_vs_public_access_method, 0.05, method="spearman")

	Pejabat jabatan kerajaan	Pusat tumpuan perkhidmatan kerajaan (spt UTC dan RTC)	Kaunter/Pejabat bergerak perkhidmatan kerajaan	Dalam talian
Age
(-0.001, 10.0]	1	0	0	0
(10.0, 20.0]	2	0	0	3
(20.0, 30.0]	4	2	3	19
(30.0, 40.0]	17	15	6	43
(40.0, 50.0]	5	7	2	14
(50.0, 60.0]	3	0	0	1

Failed to reject H_0 at alpha=0.05 since test statistic chi2=17.737781986531985 < 24.995790139728616

True

Age vs the ownership of different types of device

age_vs_ownership = relation.interval_vs_mcq(
    normalized_age, normalized_owned_devices, summary_age.index
)

relation.independence_check(age_vs_ownership, 0.05) or relation.correlation_check(
    age_vs_ownership, alpha=0.05, method="spearman"
)

	Komputer desktop	Laptop(termasuk kompter riba dan netbook)	Tablet (iPad, galaxy tab, dll)	Konsol permainan (Playstation, Nintendo Switch, Xbox)	Telefon pintar	smart tv	Android box
Age
(-0.001, 10.0]	0	1	0	0	1	0	0
(10.0, 20.0]	0	3	1	0	5	0	0
(20.0, 30.0]	4	11	4	3	23	0	0
(30.0, 40.0]	10	26	13	2	52	0	0
(40.0, 50.0]	4	6	5	3	23	1	1
(50.0, 60.0]	1	1	0	0	4	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=17.345951085437612 < 43.77297182574219

True

Age vs whether respondents get to access the internet as much as he/she desires

age_vs_sufficient_usage = relation.distinct_vs_distinct(
    normalized_edulevel, normalized_sufficient_usage, ranked_edulevel
)

relation.independence_check(
    age_vs_sufficient_usage, 0.05
) or relation.correlation_check(age_vs_sufficient_usage, 0.05, method="spearman")

sufficient_usage	Tidak	Ya	Tidak pasti/ tidak tahu
education_level
Sekolah rendah	0	0	0
Sekolah menengah	12	30	5
Institusi pengajian tinggi	20	37	4

Failed to reject H_0 at alpha=0.05 since test statistic chi2=1.045203004857124 < 5.991464547107979

True

Age vs prior experience in usage of public wifi

age_vs_used_public_wifi = relation.interval_vs_distinct(
    normalized_age, normalized_used_public_wifi, summary_age.index
)

relation.independence_check(
    age_vs_used_public_wifi, 0.05
) or relation.correlation_check(
    age_vs_used_public_wifi, alpha=0.05, method="spearman"
)

	Tidak	Tidak pasti/ tidak tahu	Ya
Age
(-0.001, 10.0]	0	1	0
(10.0, 20.0]	2	0	3
(20.0, 30.0]	12	0	12
(30.0, 40.0]	23	2	28
(40.0, 50.0]	14	1	8
(50.0, 60.0]	3	0	1

H_0 is rejected at alpha=0.05 since test statistic chi2=31.10420391521704 >= 18.307038053275146
The correlation is high at rs=0.6.
Failed to reject H_0 at alpha=0.05 since test statistic T=0.75 and critical region=±12.706204736432095. 
Hence, for None at Tidak, the correlation IS NOT significant.

The negative correlation is very low at rs=-0.030860669992418384.
Failed to reject H_0 at alpha=0.05 since test statistic T=-0.030875376054721928 and critical region=±12.706204736432095. 
Hence, for None at Tidak pasti/ tidak tahu, the correlation IS NOT significant.

The correlation is low at rs=0.2571428571428572.
Failed to reject H_0 at alpha=0.05 since test statistic T=0.2660905781950872 and critical region=±12.706204736432095. 
Hence, for None at Ya, the correlation IS NOT significant.

	Correlation
Tidak	0.600000
Tidak pasti/ tidak tahu	-0.030861
Ya	0.257143

Age vs prior experience in usage of public wifi provided by the government

age_vs_used_selangor_wifi = relation.interval_vs_distinct(
    normalized_age, normalized_used_selangor_wifi, summary_age.index
)

relation.independence_check(
    age_vs_used_selangor_wifi, 0.05
) or relation.correlation_check(
    age_vs_used_selangor_wifi, alpha=0.05, method="spearman"
)

	Tidak	Ya	Tidak pasti/ tidak tahu
Age
(-0.001, 10.0]	0	0	1
(10.0, 20.0]	2	3	0
(20.0, 30.0]	14	8	2
(30.0, 40.0]	34	17	2
(40.0, 50.0]	16	6	1
(50.0, 60.0]	4	0	0

H_0 is rejected at alpha=0.05 since test statistic chi2=22.86787290251074 >= 18.307038053275146
The correlation is high at rs=0.6.
Failed to reject H_0 at alpha=0.05 since test statistic T=0.75 and critical region=±12.706204736432095. 
Hence, for None at Tidak, the correlation IS NOT significant.

The correlation is very low at rs=0.11595420713048969.
Failed to reject H_0 at alpha=0.05 since test statistic T=0.1167416810835558 and critical region=±12.706204736432095. 
Hence, for None at Ya, the correlation IS NOT significant.

The negative correlation is very low at rs=-0.11952286093343938.
Failed to reject H_0 at alpha=0.05 since test statistic T=-0.12038585308576918 and critical region=±12.706204736432095. 
Hence, for None at Tidak pasti/ tidak tahu, the correlation IS NOT significant.

	Correlation
Tidak	0.600000
Ya	0.115954
Tidak pasti/ tidak tahu	-0.119523

Age vs ability to work from home

age_vs_wfh = relation.interval_vs_distinct(
    normalized_age, normalized_wfh, summary_age.index
)

relation.independence_check(age_vs_wfh, 0.05) or relation.correlation_check(
    age_vs_wfh, 0.05, method="spearman"
)

	Tidak	Ya	Tidak pasti/ tidak tahu
Age
(-0.001, 10.0]	1	0	0
(10.0, 20.0]	0	2	3
(20.0, 30.0]	0	21	3
(30.0, 40.0]	11	34	8
(40.0, 50.0]	4	14	5
(50.0, 60.0]	2	2	0

H_0 is rejected at alpha=0.05 since test statistic chi2=22.409321369433226 >= 18.307038053275146
The correlation is some at rs=0.5797710356524484.
Failed to reject H_0 at alpha=0.05 since test statistic T=0.7115680669648199 and critical region=±12.706204736432095. 
Hence, for None at Tidak, the correlation IS NOT significant.

The correlation is low at rs=0.3768511731740915.
Failed to reject H_0 at alpha=0.05 since test statistic T=0.4068464035508638 and critical region=±12.706204736432095. 
Hence, for None at Ya, the correlation IS NOT significant.

The correlation is low at rs=0.20597146021777488.
Failed to reject H_0 at alpha=0.05 since test statistic T=0.21048467276349228 and critical region=±12.706204736432095. 
Hence, for None at Tidak pasti/ tidak tahu, the correlation IS NOT significant.

	Correlation
Tidak	0.579771
Ya	0.376851
Tidak pasti/ tidak tahu	0.205971

Age vs being comfortable working from home

age_vs_comfortable_wfh = relation.interval_vs_distinct(
    normalized_age, normalized_comfortable_wfh, summary_age.index
)

relation.independence_check(age_vs_comfortable_wfh, 0.05) or relation.correlation_check(
    age_vs_comfortable_wfh, 0.05, method="spearman"
)

	Tidak	Ya	Tidak pasti/ tidak tahu
Age
(-0.001, 10.0]	1	0	0
(10.0, 20.0]	1	2	2
(20.0, 30.0]	4	16	4
(30.0, 40.0]	15	28	10
(40.0, 50.0]	7	14	2
(50.0, 60.0]	3	1	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=11.957605682644932 < 18.307038053275146

True

Age vs can e-learn

age_vs_can_elearn = relation.interval_vs_distinct(
    normalized_age, normalized_can_elearn, summary_age.index
)

relation.independence_check(age_vs_can_elearn, 0.05) or relation.correlation_check(
    age_vs_can_elearn, 0.05
)

	Ya	Tidak	Tidak pasti/ tidak tahu
Age
(-0.001, 10.0]	0	1	0
(10.0, 20.0]	2	1	2
(20.0, 30.0]	15	4	5
(30.0, 40.0]	34	15	4
(40.0, 50.0]	18	3	2
(50.0, 60.0]	3	1	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=13.150878864208439 < 18.307038053275146

True

Age vs comfortable e-learn

age_vs_comfortable_elearn = relation.interval_vs_distinct(
    normalized_age, normalized_comfortable_elearn, summary_age.index
)

relation.independence_check(
    age_vs_comfortable_elearn, 0.05
) or relation.correlation_check(
    age_vs_comfortable_elearn, alpha=0.05, method="spearman"
)

	Tidak	Ya	Tidak pasti/ tidak tahu
Age
(-0.001, 10.0]	1	0	0
(10.0, 20.0]	1	1	3
(20.0, 30.0]	6	11	7
(30.0, 40.0]	20	25	8
(40.0, 50.0]	7	11	5
(50.0, 60.0]	2	2	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=10.367134550643662 < 18.307038053275146

True

Age vs budget for internet access

age_vs_budget_internet = relation.interval_vs_interval(
    normalized_age,
    normalized_budget_internet,
    summary_age.index,
    summary_budget_internet.index,
)

relation.independence_check(
    age_vs_budget_internet, 0.05
) or relation.correlation_check(
    age_vs_budget_internet, alpha=0.05, method="spearman"
)

budget internet	(-0.001, 50.0]	(50.0, 100.0]	(100.0, 150.0]	(150.0, 200.0]	(200.0, 250.0]	(250.0, 300.0]	(300.0, 350.0]	(350.0, 400.0]	(400.0, 450.0]	(450.0, 500.0]
Age
(-0.001, 10.0]	0	0	0	0	0	0	0	0	0	0
(10.0, 20.0]	4	1	0	0	0	0	0	0	0	0
(20.0, 30.0]	13	8	1	1	0	0	0	0	0	0
(30.0, 40.0]	30	16	2	3	0	0	0	0	0	1
(40.0, 50.0]	14	8	0	1	0	0	0	0	0	0
(50.0, 60.0]	3	1	0	0	0	0	0	0	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=3.9201242192110963 < 26.29622760486423

True

Age vs Budget for computer / laptop

age_vs_budget_computer = relation.interval_vs_interval(
    normalized_age,
    normalized_budget_computer,
    summary_age.index,
    summary_budget_computer.index,
)

relation.independence_check(age_vs_budget_computer, 0.05) or relation.correlation_check(
    age_vs_budget_computer, 0.05, method="spearman"
)

budget computer	(-0.001, 100.0]	(100.0, 200.0]	(200.0, 300.0]	(300.0, 400.0]	(400.0, 500.0]	(500.0, 600.0]	(600.0, 700.0]	(700.0, 800.0]
Age
(-0.001, 10.0]	0	0	0	0	0	0	0	0
(10.0, 20.0]	1	0	0	0	0	0	0	0
(20.0, 30.0]	3	0	0	0	3	0	0	0
(30.0, 40.0]	6	2	5	0	6	0	5	3
(40.0, 50.0]	3	5	2	0	1	0	0	0
(50.0, 60.0]	1	0	0	0	1	0	1	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=24.15619397437579 < 31.410432844230918

True

Age vs budget for mobile devices

age_vs_budget_mobile = relation.interval_vs_interval(
    normalized_age,
    normalized_budget_mobile,
    summary_age.index,
    summary_budget_mobile.index,
)

relation.independence_check(
    age_vs_budget_mobile, 0.05
) or relation.correlation_check(age_vs_budget_mobile, 0.05, method="spearman")

budget mobile	(-0.001, 100.0]	(100.0, 200.0]	(200.0, 300.0]	(300.0, 400.0]	(400.0, 500.0]	(500.0, 600.0]	(600.0, 700.0]	(700.0, 800.0]
Age
(-0.001, 10.0]	0	0	0	0	0	0	0	0
(10.0, 20.0]	1	0	0	0	2	0	1	1
(20.0, 30.0]	4	1	0	1	5	1	0	0
(30.0, 40.0]	6	2	8	0	12	3	3	4
(40.0, 50.0]	5	4	1	1	3	0	1	2
(50.0, 60.0]	2	0	0	0	1	1	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=27.4154543363239 < 41.33713815142739

True

vs Gender (Skipping correlation tests)

ranked_gender = pd.Series(['Lelaki', 'Perempuan', 'Transgender'], name=fields.FIELD_GENDER)

Gender vs methods used to access government service

gender_vs_public_access_method = relation.distinct_vs_mcq(
    normalized_gender,
    normalized_public_access_method,
    ranked_gender
)

relation.independence_check(gender_vs_public_access_method, 0.05)

	Pejabat jabatan kerajaan	Pusat tumpuan perkhidmatan kerajaan (spt UTC dan RTC)	Kaunter/Pejabat bergerak perkhidmatan kerajaan	Dalam talian
gender
Lelaki	14	6	2	19
Perempuan	12	13	5	37
Transgender	0	0	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=3.763054832623549 < 7.814727903251179

True

Gender vs ownership of different types of devices

gender_vs_ownership = relation.distinct_vs_mcq(
    normalized_gender, normalized_owned_devices, ranked_gender
)

relation.independence_check(gender_vs_ownership, 0.05)

	Komputer desktop	Laptop(termasuk kompter riba dan netbook)	Tablet (iPad, galaxy tab, dll)	Konsol permainan (Playstation, Nintendo Switch, Xbox)	Telefon pintar	smart tv	Android box
gender
Lelaki	9	14	7	3	27	0	0
Perempuan	7	23	11	3	52	0	0
Transgender	0	0	0	0	0	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=3.0966906978180715 < 9.487729036781154

True

Gender vs whether respondents get to access the internet as much as they desire

gender_vs_sufficient_usage = relation.distinct_vs_distinct(
    normalized_gender, normalized_sufficient_usage, ranked_gender
)

relation.independence_check(gender_vs_sufficient_usage, 0.05) 

sufficient_usage	Tidak	Ya	Tidak pasti/ tidak tahu
gender
Lelaki	10	17	2
Perempuan	10	37	5
Transgender	0	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=2.351885183781736 < 5.991464547107979

True

Gender vs prior experience in usage of public wifi

gender_vs_used_public_wifi = relation.distinct_vs_distinct(
    normalized_gender, normalized_used_public_wifi, ranked_gender
)

relation.independence_check(gender_vs_used_public_wifi, 0.05)

used_public_wifi	Tidak	Tidak pasti/ tidak tahu	Ya
gender
Lelaki	15	1	13
Perempuan	26	1	25
Transgender	0	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=0.22823077944586498 < 5.991464547107979

True

Gender vs prior experience in usage of public wifi provided by the government

gender_vs_used_selangor_wifi = relation.distinct_vs_distinct(
    normalized_gender, normalized_used_selangor_wifi, ranked_gender
)

relation.independence_check(
    gender_vs_used_selangor_wifi, 0.05
)

used_selangor_wifi	Tidak	Ya	Tidak pasti/ tidak tahu
gender
Lelaki	18	8	3
Perempuan	32	17	3
Transgender	0	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=0.6843103448275859 < 5.991464547107979

True

Gender vs ability to work from home

gender_vs_wfh = relation.distinct_vs_distinct(
    normalized_gender,
    normalized_wfh,
    ranked_gender
)

relation.independence_check(gender_vs_wfh, 0.05)

can_work_from_home	Tidak	Ya	Tidak pasti/ tidak tahu
gender
Lelaki	5	16	8
Perempuan	6	38	8
Transgender	0	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=2.7442729684108995 < 5.991464547107979

True

Gender vs Comfortable working from home

gender_vs_comfortable_wfh = relation.distinct_vs_distinct(
    normalized_gender,
    normalized_comfortable_wfh,
    ranked_gender
)

relation.independence_check(gender_vs_comfortable_wfh, 0.05)

comfy_work_from_home	Tidak	Ya	Tidak pasti/ tidak tahu
gender
Lelaki	8	14	7
Perempuan	12	31	9
Transgender	0	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=1.0239141246684351 < 5.991464547107979

True

Gender vs can e-learn

gender_vs_can_elearn = relation.distinct_vs_distinct(
    normalized_gender,
    normalized_can_elearn,
    ranked_gender
)

relation.independence_check(gender_vs_can_elearn, 0.05)

family_can_elearn	Ya	Tidak	Tidak pasti/ tidak tahu
gender
Lelaki	17	8	4
Perempuan	37	8	7
Transgender	0	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=1.8433506149023393 < 5.991464547107979

True

Gender vs comfortable e-learn

gender_vs_budget_internet = relation.distinct_vs_interval(
    normalized_gender,
    normalized_budget_internet,
    ranked_gender,
    summary_budget_internet.index,
)

relation.independence_check(gender_vs_budget_internet, 0.05)

budget internet	(-0.001, 50.0]	(50.0, 100.0]	(100.0, 150.0]	(150.0, 200.0]	(200.0, 250.0]	(250.0, 300.0]	(300.0, 350.0]	(350.0, 400.0]	(400.0, 450.0]	(450.0, 500.0]
gender
Lelaki	16	8	1	2	0	0	0	0	0	1
Perempuan	33	15	1	3	0	0	0	0	0	0
Transgender	0	0	0	0	0	0	0	0	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=2.2290043585518298 < 9.487729036781154

True

Gender vs budget for internet access

gender_vs_budget_internet = relation.distinct_vs_interval(
    normalized_gender,
    normalized_budget_internet,
    ranked_gender,
    summary_budget_internet.index,
)

relation.independence_check(gender_vs_budget_internet, 0.05)

budget internet	(-0.001, 50.0]	(50.0, 100.0]	(100.0, 150.0]	(150.0, 200.0]	(200.0, 250.0]	(250.0, 300.0]	(300.0, 350.0]	(350.0, 400.0]	(400.0, 450.0]	(450.0, 500.0]
gender
Lelaki	16	8	1	2	0	0	0	0	0	1
Perempuan	33	15	1	3	0	0	0	0	0	0
Transgender	0	0	0	0	0	0	0	0	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=2.2290043585518298 < 9.487729036781154

True

Gender vs budget for computer / laptop

gender_vs_budget_computer = relation.distinct_vs_interval(
    normalized_gender,
    normalized_budget_computer,
    ranked_gender,
    summary_budget_computer.index,
)

relation.independence_check(gender_vs_budget_computer, 0.05)

budget computer	(-0.001, 100.0]	(100.0, 200.0]	(200.0, 300.0]	(300.0, 400.0]	(400.0, 500.0]	(500.0, 600.0]	(600.0, 700.0]	(700.0, 800.0]
gender
Lelaki	3	1	1	0	5	0	2	1
Perempuan	7	4	3	0	5	0	4	1
Transgender	0	0	0	0	0	0	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=1.970566239316239 < 11.070497693516351

True

Gender vs budget for mobile devices

gender_vs_budget_mobile = relation.distinct_vs_interval(
    normalized_gender,
    normalized_budget_mobile,
    ranked_gender,
    summary_budget_mobile.index,
)

relation.independence_check(
    gender_vs_budget_mobile, 0.05
)

budget mobile	(-0.001, 100.0]	(100.0, 200.0]	(200.0, 300.0]	(300.0, 400.0]	(400.0, 500.0]	(500.0, 600.0]	(600.0, 700.0]	(700.0, 800.0]
gender
Lelaki	3	2	4	0	8	2	2	1
Perempuan	10	2	5	2	10	2	3	3
Transgender	0	0	0	0	0	0	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=3.7301061551061556 < 14.067140449340169

True

Employment status vs

ranked_employment = pd.Series(
    [
        "Bekerja dengan bergaji (sepenuh masa/ separuh masa)",
        "Bekerja sendiri/ pemilik perniagaan",
        "Pelajar (sepenuh masa /separuh masa)",
        "Tidak bekerja kerana sakit atau kurang upaya",
        "Menganggur / tidak bekerja ( tiada kerja / sedang mencari kerja)",
        "Tentera / Polis / Badan Beruniform",
        "Pesara / Pencen",
        "Memilih tidak menjawab",
    ],
    name=fields.FIELD_EMPLOYMENT_STATUS
)

Employment status vs methods used to access government service

employment_vs_public_access_method = relation.distinct_vs_mcq(
    normalized_employment,
    normalized_public_access_method,
    ranked_employment
)

relation.independence_check(employment_vs_public_access_method, 0.05)

	Pejabat jabatan kerajaan	Pusat tumpuan perkhidmatan kerajaan (spt UTC dan RTC)	Kaunter/Pejabat bergerak perkhidmatan kerajaan	Dalam talian
employment_status
Bekerja dengan bergaji (sepenuh masa/ separuh masa)	22	16	7	50
Bekerja sendiri/ pemilik perniagaan	3	6	4	11
Pelajar (sepenuh masa /separuh masa)	2	0	0	4
Tidak bekerja kerana sakit atau kurang upaya	0	0	0	0
Menganggur / tidak bekerja ( tiada kerja / sedang mencari kerja)	3	0	0	8
Tentera / Polis / Badan Beruniform	0	0	0	1
Pesara / Pencen	0	0	0	0
Memilih tidak menjawab	1	0	0	2

Failed to reject H_0 at alpha=0.05 since test statistic chi2=12.348367397502864 < 24.995790139728616

True

Employment status vs the ownership of different types of devices

employment_vs_ownership = relation.distinct_vs_mcq(
    normalized_employment, normalized_owned_devices, ranked_employment
)

relation.independence_check(employment_vs_ownership, 0.05)

	Komputer desktop	Laptop(termasuk kompter riba dan netbook)	Tablet (iPad, galaxy tab, dll)	Konsol permainan (Playstation, Nintendo Switch, Xbox)	Telefon pintar	smart tv	Android box
employment_status
Bekerja dengan bergaji (sepenuh masa/ separuh masa)	14	31	16	6	65	1	1
Bekerja sendiri/ pemilik perniagaan	2	6	4	1	16	0	0
Pelajar (sepenuh masa /separuh masa)	1	3	1	0	5	0	0
Tidak bekerja kerana sakit atau kurang upaya	0	0	0	0	0	0	0
Menganggur / tidak bekerja ( tiada kerja / sedang mencari kerja)	1	4	1	0	11	0	0
Tentera / Polis / Badan Beruniform	0	1	1	1	1	0	0
Pesara / Pencen	0	0	0	0	0	0	0
Memilih tidak menjawab	1	1	0	0	3	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=11.90457107742921 < 43.77297182574219

True

Employment status vs whether respondents get to access the internet as much as they desire

employment_vs_sufficient_usage = relation.distinct_vs_distinct(
    normalized_employment, normalized_sufficient_usage, ranked_employment
)

relation.independence_check(employment_vs_sufficient_usage, 0.05) 

sufficient_usage	Tidak	Ya	Tidak pasti/ tidak tahu
employment_status
Bekerja dengan bergaji (sepenuh masa/ separuh masa)	19	44	3
Bekerja sendiri/ pemilik perniagaan	3	10	3
Pelajar (sepenuh masa /separuh masa)	3	3	0
Tidak bekerja kerana sakit atau kurang upaya	0	0	0
Menganggur / tidak bekerja ( tiada kerja / sedang mencari kerja)	3	6	2
Tentera / Polis / Badan Beruniform	1	0	0
Pesara / Pencen	0	0	0
Memilih tidak menjawab	1	2	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=9.988754127816629 < 18.307038053275146

True

Employment status vs prior experience in usage of public wifi

employment_vs_used_public_wifi = relation.distinct_vs_distinct(
    normalized_employment, normalized_used_public_wifi, ranked_employment
)

relation.independence_check(employment_vs_used_public_wifi, 0.05)

used_public_wifi	Tidak	Tidak pasti/ tidak tahu	Ya
employment_status
Bekerja dengan bergaji (sepenuh masa/ separuh masa)	34	2	30
Bekerja sendiri/ pemilik perniagaan	7	0	9
Pelajar (sepenuh masa /separuh masa)	1	0	5
Tidak bekerja kerana sakit atau kurang upaya	0	0	0
Menganggur / tidak bekerja ( tiada kerja / sedang mencari kerja)	6	1	4
Tentera / Polis / Badan Beruniform	1	0	0
Pesara / Pencen	0	0	0
Memilih tidak menjawab	2	1	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=14.889109384284016 < 18.307038053275146

True

Employment status vs prior experience in usage of public wifi provided by the government

employment_vs_used_selangor_wifi = relation.distinct_vs_distinct(
    normalized_employment, normalized_used_selangor_wifi, ranked_employment
)

relation.independence_check(
    employment_vs_used_selangor_wifi, 0.05
)

used_selangor_wifi	Tidak	Ya	Tidak pasti/ tidak tahu
employment_status
Bekerja dengan bergaji (sepenuh masa/ separuh masa)	40	23	3
Bekerja sendiri/ pemilik perniagaan	11	5	0
Pelajar (sepenuh masa /separuh masa)	1	4	1
Tidak bekerja kerana sakit atau kurang upaya	0	0	0
Menganggur / tidak bekerja ( tiada kerja / sedang mencari kerja)	9	1	1
Tentera / Polis / Badan Beruniform	1	0	0
Pesara / Pencen	0	0	0
Memilih tidak menjawab	2	0	1

Failed to reject H_0 at alpha=0.05 since test statistic chi2=15.046049091769973 < 18.307038053275146

True

Employment status vs ability to work from home

employment_vs_wfh = relation.distinct_vs_distinct(
    normalized_employment,
    normalized_wfh,
    ranked_employment
)

relation.independence_check(employment_vs_wfh, 0.05)

can_work_from_home	Tidak	Ya	Tidak pasti/ tidak tahu
employment_status
Bekerja dengan bergaji (sepenuh masa/ separuh masa)	16	39	11
Bekerja sendiri/ pemilik perniagaan	1	12	3
Pelajar (sepenuh masa /separuh masa)	0	4	2
Tidak bekerja kerana sakit atau kurang upaya	0	0	0
Menganggur / tidak bekerja ( tiada kerja / sedang mencari kerja)	0	10	1
Tentera / Polis / Badan Beruniform	0	1	0
Pesara / Pencen	0	0	0
Memilih tidak menjawab	1	1	1

Failed to reject H_0 at alpha=0.05 since test statistic chi2=10.800985602291572 < 18.307038053275146

True

Employment status vs being comfortable working from home

employment_vs_comfortable_wfh = relation.distinct_vs_distinct(
    normalized_employment,
    normalized_comfortable_wfh,
    ranked_employment
)

relation.independence_check(employment_vs_comfortable_wfh, 0.05)

comfy_work_from_home	Tidak	Ya	Tidak pasti/ tidak tahu
employment_status
Bekerja dengan bergaji (sepenuh masa/ separuh masa)	25	30	11
Bekerja sendiri/ pemilik perniagaan	3	12	1
Pelajar (sepenuh masa /separuh masa)	1	2	3
Tidak bekerja kerana sakit atau kurang upaya	0	0	0
Menganggur / tidak bekerja ( tiada kerja / sedang mencari kerja)	1	9	1
Tentera / Polis / Badan Beruniform	0	1	0
Pesara / Pencen	0	0	0
Memilih tidak menjawab	1	1	1

Failed to reject H_0 at alpha=0.05 since test statistic chi2=15.368564199873498 < 18.307038053275146

True

Employment status vs can e-learn

employment_vs_can_elearn = relation.distinct_vs_distinct(
    normalized_employment,
    normalized_can_elearn,
    ranked_employment
)

relation.independence_check(employment_vs_can_elearn, 0.05)

family_can_elearn	Ya	Tidak	Tidak pasti/ tidak tahu
employment_status
Bekerja dengan bergaji (sepenuh masa/ separuh masa)	39	17	10
Bekerja sendiri/ pemilik perniagaan	11	3	2
Pelajar (sepenuh masa /separuh masa)	4	2	0
Tidak bekerja kerana sakit atau kurang upaya	0	0	0
Menganggur / tidak bekerja ( tiada kerja / sedang mencari kerja)	9	2	0
Tentera / Polis / Badan Beruniform	1	0	0
Pesara / Pencen	0	0	0
Memilih tidak menjawab	1	1	1

Failed to reject H_0 at alpha=0.05 since test statistic chi2=6.111573426573426 < 18.307038053275146

True

Employment status vs comfortable e-learn

employment_vs_comfortable_elearn = relation.distinct_vs_distinct(
    normalized_employment, normalized_comfortable_elearn, ranked_employment
)

relation.independence_check(employment_vs_comfortable_elearn, 0.05)

comfy_elearn	Tidak	Ya	Tidak pasti/ tidak tahu
employment_status
Bekerja dengan bergaji (sepenuh masa/ separuh masa)	27	25	14
Bekerja sendiri/ pemilik perniagaan	4	8	4
Pelajar (sepenuh masa /separuh masa)	2	2	2
Tidak bekerja kerana sakit atau kurang upaya	0	0	0
Menganggur / tidak bekerja ( tiada kerja / sedang mencari kerja)	3	7	1
Tentera / Polis / Badan Beruniform	0	1	0
Pesara / Pencen	0	0	0
Memilih tidak menjawab	1	1	1

Failed to reject H_0 at alpha=0.05 since test statistic chi2=5.927043779316508 < 18.307038053275146

True

Employment status vs budget for internet access

employment_vs_budget_internet = relation.distinct_vs_interval(
    normalized_employment,
    normalized_budget_internet,
    ranked_employment,
    summary_budget_internet.index,
)

relation.independence_check(employment_vs_budget_internet, 0.05)

budget internet	(-0.001, 50.0]	(50.0, 100.0]	(100.0, 150.0]	(150.0, 200.0]	(200.0, 250.0]	(250.0, 300.0]	(300.0, 350.0]	(350.0, 400.0]	(400.0, 450.0]	(450.0, 500.0]
employment_status
Bekerja dengan bergaji (sepenuh masa/ separuh masa)	35	21	3	5	0	0	0	0	0	1
Bekerja sendiri/ pemilik perniagaan	10	5	0	0	0	0	0	0	0	0
Pelajar (sepenuh masa /separuh masa)	6	0	0	0	0	0	0	0	0	0
Tidak bekerja kerana sakit atau kurang upaya	0	0	0	0	0	0	0	0	0	0
Menganggur / tidak bekerja ( tiada kerja / sedang mencari kerja)	8	3	0	0	0	0	0	0	0	0
Tentera / Polis / Badan Beruniform	0	1	0	0	0	0	0	0	0	0
Pesara / Pencen	0	0	0	0	0	0	0	0	0	0
Memilih tidak menjawab	1	1	0	0	0	0	0	0	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=11.638030428353007 < 31.410432844230918

True

Employment status vs budget for computer / laptop

employment_vs_budget_computer = relation.distinct_vs_interval(
    normalized_employment,
    normalized_budget_computer,
    ranked_employment,
    summary_budget_computer.index,
)

relation.independence_check(
    employment_vs_budget_computer, 0.05
)

budget computer	(-0.001, 100.0]	(100.0, 200.0]	(200.0, 300.0]	(300.0, 400.0]	(400.0, 500.0]	(500.0, 600.0]	(600.0, 700.0]	(700.0, 800.0]
employment_status
Bekerja dengan bergaji (sepenuh masa/ separuh masa)	9	4	4	0	7	0	5	2
Bekerja sendiri/ pemilik perniagaan	1	1	0	0	2	0	0	0
Pelajar (sepenuh masa /separuh masa)	0	0	0	0	1	0	0	0
Tidak bekerja kerana sakit atau kurang upaya	0	0	0	0	0	0	0	0
Menganggur / tidak bekerja ( tiada kerja / sedang mencari kerja)	3	0	0	0	1	0	1	1
Tentera / Polis / Badan Beruniform	0	0	0	0	0	0	0	0
Pesara / Pencen	0	0	0	0	0	0	0	0
Memilih tidak menjawab	0	1	0	0	0	0	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=15.497734792089632 < 31.410432844230918

True

Employment status vs budget for mobile devices

employment_vs_budget_mobile = relation.distinct_vs_interval(
    normalized_employment,
    normalized_budget_mobile,
    ranked_employment,
    summary_budget_mobile.index,
)

relation.independence_check(employment_vs_budget_mobile, 0.05)

budget mobile	(-0.001, 100.0]	(100.0, 200.0]	(200.0, 300.0]	(300.0, 400.0]	(400.0, 500.0]	(500.0, 600.0]	(600.0, 700.0]	(700.0, 800.0]
employment_status
Bekerja dengan bergaji (sepenuh masa/ separuh masa)	8	4	7	1	15	3	4	3
Bekerja sendiri/ pemilik perniagaan	2	1	0	0	3	0	0	2
Pelajar (sepenuh masa /separuh masa)	0	1	0	1	1	1	1	1
Tidak bekerja kerana sakit atau kurang upaya	0	0	0	0	0	0	0	0
Menganggur / tidak bekerja ( tiada kerja / sedang mencari kerja)	5	0	1	0	2	0	0	1
Tentera / Polis / Badan Beruniform	0	0	0	0	0	0	0	0
Pesara / Pencen	0	0	0	0	0	0	0	0
Memilih tidak menjawab	0	1	0	0	1	0	0	0

Failed to reject H_0 at alpha=0.05 since test statistic chi2=27.046212121212122 < 41.33713815142739

True